added tie_weights support to mlp speculator

[JRosenkranz]

What does this PR do?

Currently MLPSpeculator does not support tie_weights. Many newer trained speculators with MLPSpeculator architecture are using this feature, which makes the speculator much smaller.

• added tie_weights configuration to the speculator
• added scale_input configuration to the speculator
• fixed loading when speculator has non-safetensors

To reproduce:

text-generation-launcher --model-id ibm-granite/granite-3b-code-instruct-accelerator

Before submitting

• [ ] This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case).
• [ ] Did you read the contributor guideline, Pull Request section?
• [ ] Was this discussed/approved via a Github issue or the forum? Please add a link to it if that's the case.
• [ ] Did you make sure to update the documentation with your changes? Here are the documentation guidelines, and here are tips on formatting docstrings.
• [ ] Did you write any new necessary tests?

Who can review?

Anyone in the community is free to review the PR once the tests have passed. Feel free to tag members/contributors who may be interested in your PR.

@Narsil